One install → every tool for your AI agent. Wallet-native, pay-per-call, no keys (x402).
Single tool 'list_timezones' has a basic description but critically lacks a complete input schema in the visible source. The description is generic (47 chars) and provides minimal context for LLM selection. No output schema is documented. The tool is exposed via a remote HTTP MCP server (src/proxy.ts bridges to https://api.agishub.com/mcp), but the actual tool definition is not visible in the provided source, only a reference in src/try.ts.
List timezones matching a query (free tool available over MCP)
Input schema not visible in source code. Only a parameter 'query' is mentioned in comments; no JSON Schema with type, format, or constraints is shown.
Output schema completely undocumented. No description of what list_timezones returns (structure, fields, pagination).
Tool description is generic and under 50 chars ('List timezones matching a query...'). Does not explain WHEN to use it, WHAT it returns, or WHY an LLM should select it over alternatives.
Parameter 'query' lacks a formal description. The inline comment 'Timezone query string (e.g. kolkata)' is not a proper parameter annotation and includes an example value that LLMs may reuse literally.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
Tool definition is inferred from src/try.ts and src/proxy.ts (which forward to a remote hub). The actual schema is not visible in this repository, it lives on https://api.agishub.com/mcp.